DocumentCode
3784021
Title
Evaluation of holistic features for word recognition
Author
J.J. de Oliveira;J.M. de Carvalho
Author_Institution
Dept. of Electr. Eng., Univ. Fed. da Paraiba, Joao Pessoa, Brazil
fYear
2001
fDate
6/23/1905 12:00:00 AM
Firstpage
394
Abstract
This work proposes a testing environment for evaluation of holistic methods for word recognition. The main goal is to determine an optimum set of holistic characteristics to represent the months of the year in Brazilian Portuguese language. The holistic characteristics treat the words as single, indivisible entities and attempts to perform recognition from their overall shape, as opposed to their character contents. No segmentation step is needed in holistic recognition systems.
Keywords
"Testing","Character recognition","Handwriting recognition","Neural networks","Shape","Image databases","Spatial databases","Cities and towns","Filtering","Performance evaluation"
Publisher
ieee
Conference_Titel
Computer Graphics and Image Processing, 2001 Proceedings of XIV Brazilian Symposium on
Print_ISBN
0-7695-1330-1
Type
conf
DOI
10.1109/SIBGRAPI.2001.963100
Filename
963100
Link To Document